{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MYSXRZRCOUY34XWI23YUN6YXUM","short_pith_number":"pith:MYSXRZRC","schema_version":"1.0","canonical_sha256":"662578e6227531be5ec8d6f146fb17a33d33711bf76efb7e72954ed763c659f2","source":{"kind":"arxiv","id":"1912.11006","version":3},"attestation_state":"computed","paper":{"title":"Data-Free Adversarial Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengchao Shen, Da Chen, Gongfan Fang, Jie Song, Mingli Song, Xinchao Wang","submitted_at":"2019-12-23T18:08:33Z","abstract_excerpt":"Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large amount of original training data or alternative data, which is usually unavailable in real-world scenarios. In this paper, we devote ourselves to this challenging problem and propose a novel adversarial distillation mechanism to craft a compact student model without any real-world data. We introduce a model discrepancy to quantificationally measure the diffe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.11006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-23T18:08:33Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"78ccd5be0f441e7189405063cb62ff457df6af5721a91d40d1e58cb7448c8adf","abstract_canon_sha256":"f9992ced1e17f7b819c07449450d35f0e7fa5cdc40a6051f3da8f048b438a00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:42.067592Z","signature_b64":"/PxbZaQZb5z6QwtlCL8OZhn0Et+mUyPazf1gq7aQNtxnI+Bmz9BNWw+GT8N9JUsxZTPg5fyfBxkR/ARCHncwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"662578e6227531be5ec8d6f146fb17a33d33711bf76efb7e72954ed763c659f2","last_reissued_at":"2026-07-05T00:44:42.067152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:42.067152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Free Adversarial Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengchao Shen, Da Chen, Gongfan Fang, Jie Song, Mingli Song, Xinchao Wang","submitted_at":"2019-12-23T18:08:33Z","abstract_excerpt":"Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large amount of original training data or alternative data, which is usually unavailable in real-world scenarios. In this paper, we devote ourselves to this challenging problem and propose a novel adversarial distillation mechanism to craft a compact student model without any real-world data. We introduce a model discrepancy to quantificationally measure the diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11006","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.11006/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.11006","created_at":"2026-07-05T00:44:42.067208+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11006v3","created_at":"2026-07-05T00:44:42.067208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11006","created_at":"2026-07-05T00:44:42.067208+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYSXRZRCOUY3","created_at":"2026-07-05T00:44:42.067208+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYSXRZRCOUY34XWI","created_at":"2026-07-05T00:44:42.067208+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYSXRZRC","created_at":"2026-07-05T00:44:42.067208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27409","citing_title":"STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM","json":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM.json","graph_json":"https://pith.science/api/pith-number/MYSXRZRCOUY34XWI23YUN6YXUM/graph.json","events_json":"https://pith.science/api/pith-number/MYSXRZRCOUY34XWI23YUN6YXUM/events.json","paper":"https://pith.science/paper/MYSXRZRC"},"agent_actions":{"view_html":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM","download_json":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM.json","view_paper":"https://pith.science/paper/MYSXRZRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11006&json=true","fetch_graph":"https://pith.science/api/pith-number/MYSXRZRCOUY34XWI23YUN6YXUM/graph.json","fetch_events":"https://pith.science/api/pith-number/MYSXRZRCOUY34XWI23YUN6YXUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM/action/storage_attestation","attest_author":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM/action/author_attestation","sign_citation":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM/action/citation_signature","submit_replication":"https://pith.science/pith/MYSXRZRCOUY34XWI23YUN6YXUM/action/replication_record"}},"created_at":"2026-07-05T00:44:42.067208+00:00","updated_at":"2026-07-05T00:44:42.067208+00:00"}